Visualizing Data with Seaborn (Python Track)

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

from matplotlib import rcParams

# Set global font properties to Arial
rcParams.update(
    {
        "font.family": "sans-serif",
        "font.sans-serif": "Arial",
        "pdf.fonttype": 42,  # Embed fonts as Type 3 fonts for compatibility
        "ps.fonttype": 42,
        "text.usetex": False,
        "svg.fonttype": "none",
    }
)


def stardize_columns(df):
    df.columns = [" ".join(col.strip().split()) for col in df.columns]


# Load the data
df = pd.read_csv("Crimes_One_year_prior_to_present_first_1001.csv")
stardize_columns(df)

# Display basic information about the dataset
print(df.info())

# Show the first few rows
print(df.head(3))

# Basic data cleaning
df["DATE OF OCCURRENCE"] = pd.to_datetime(df["DATE OF OCCURRENCE"])

plt.figure(figsize=(12, 6))
sns.countplot(data=df, y='PRIMARY DESCRIPTION', order=df['PRIMARY DESCRIPTION'].value_counts().index[:10])
plt.title('Top 10 Crime Types')
plt.show()

df['DAY_OF_WEEK'] = df['DATE OF OCCURRENCE'].dt.day_name()
plt.figure(figsize=(12, 6))
sns.boxplot(data=df, x='DAY_OF_WEEK', y='DATE OF OCCURRENCE').set_ylabel('Date')
plt.title('Distribution of Crimes by Day of the Week')
plt.show()

df['HOUR'] = df['DATE OF OCCURRENCE'].dt.hour
plt.figure(figsize=(12, 6))
sns.histplot(data=df, x='HOUR', bins=24, kde=True)
plt.title('Distribution of Crimes by Hour of the Day')
plt.show()

plt.figure(figsize=(12, 6))
sns.kdeplot(data=df, x='HOUR', hue='PRIMARY DESCRIPTION', common_norm=False)
plt.title('Distribution of Different Crime Types by Hour')
plt.show()

plt.figure(figsize=(12, 10))
sns.scatterplot(data=df, x="LONGITUDE", y="LATITUDE", hue="PRIMARY DESCRIPTION")
plt.title("Geographical Distribution of Crimes")
plt.show()

crime_counts = df.groupby('DATE OF OCCURRENCE').size().reset_index(name='COUNT')
plt.figure(figsize=(12, 6))
sns.lineplot(data=crime_counts, x='DATE OF OCCURRENCE', y='COUNT')
plt.title('Crime Trends Over Time')
plt.xticks(rotation=45)
plt.show()

plt.figure(figsize=(14, 8))
sns.set_style("whitegrid")
sns.set_palette("deep")

g = sns.countplot(
    data=df,
    y="PRIMARY DESCRIPTION",
    order=df["PRIMARY DESCRIPTION"].value_counts().index[:10],
)

g.set_title("Top 10 Crime Types", fontsize=20)
g.set_xlabel("Count", fontsize=14)
g.set_ylabel("Crime Type", fontsize=14)

for i, v in enumerate(df["PRIMARY DESCRIPTION"].value_counts()[:10]):
    g.text(v + 3, i, str(v), color="black", va="center")

plt.tight_layout()
plt.show()

# Select numeric columns
numeric_cols = df.select_dtypes(include=[np.number]).columns

# Compute correlation matrix
corr_matrix = df[numeric_cols].corr()

# Create heatmap
plt.figure(figsize=(12, 10))
sns.heatmap(corr_matrix, annot=True, cmap="coolwarm", linewidths=0.5)
plt.title("Correlation Heatmap of Numeric Variables")
plt.show()

# Select numeric columns
numeric_cols = df.select_dtypes(include=[np.number]).columns

# Compute correlation matrix
corr_matrix = df[numeric_cols].corr()

# Create a mask for the upper triangle
mask = np.triu(np.ones_like(corr_matrix, dtype=bool))

# Set up the matplotlib figure
plt.figure(figsize=(14, 10))

# Create heatmap with only upper triangle
sns.heatmap(
    corr_matrix,
    mask=mask,
    annot=True,
    cmap="coolwarm",
    vmin=-1,
    vmax=1,
    center=0,
    square=True,
    linewidths=0.5,
    cbar_kws={"shrink": 0.8},
    fmt=".2f",
)

plt.title("Upper Triangle Correlation Heatmap of Numeric Variables", fontsize=16)
plt.tight_layout()
plt.show()

# Select relevant columns for the pair plot
cols_to_plot = ["X COORDINATE", "Y COORDINATE", "LATITUDE", "LONGITUDE"]

# Add hour of day
df["HOUR"] = pd.to_datetime(df["DATE OF OCCURRENCE"]).dt.hour

# Create the pair plot
plt.figure(figsize=(10, 10))
pairplot = sns.pairplot(
    df[cols_to_plot + ["HOUR", "PRIMARY DESCRIPTION"]],
    hue="PRIMARY DESCRIPTION",
    palette="viridis",
    plot_kws={"alpha": 0.6},
    diag_kind="kde",
)

plt.suptitle("Pair Plot of Geographic Variables and Hour of Occurrence", y=1.02)
plt.tight_layout()
plt.show()

sns.lmplot(
    data=df,
    x="BEAT",
    y="WARD",
    col="ARREST",
    row="DOMESTIC",
    height=3,
    facet_kws=dict(sharex=False, sharey=False),
    scatter_kws={"alpha": 0.5},
)
plt.title("Regression Plot: Latitude vs Longitude of Crime Occurrences")
plt.show()

# Group data by day of week and calculate mean crime count
crime_by_day = df.groupby("DAY_OF_WEEK").size().reset_index(name="COUNT")

plt.figure(figsize=(12, 8))
sns.barplot(
    data=crime_by_day, x="DAY_OF_WEEK", y="COUNT", errorbar=("ci", 95), capsize=0.2
)
plt.title("Average Crime Count by Day of Week with 95% Confidence Intervals")
plt.xticks(rotation=45)
plt.show()

# Create a FacetGrid
plt.figure(figsize=(20, 20))
g = sns.FacetGrid(df, col="PRIMARY DESCRIPTION", col_wrap=3, height=4, aspect=1.5)

# Map a histogram to each subplot
g.map(plt.hist, "HOUR", bins=24)

# Customize the plot
g.set_axis_labels("Hour of Day", "Count")
g.set_titles("{col_name}")
g.fig.suptitle("Distribution of Crimes by Hour for Different Crime Types", y=1.02)
g.tight_layout()
plt.show()